Triple
T17111502
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tseng |
E415235
|
entity |
| Predicate | romanizationType |
P125986
|
FINISHED |
| Object | surname romanization |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: surname romanization | Statement: [Tseng, romanizationType, surname romanization]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: romanizationType Context triple: [Tseng, romanizationType, surname romanization]
-
A.
romanizationOfToponymType
Indicates a relationship where a specific type of place-name is expressed in a romanized (Latin-script) form corresponding to its original writing system.
-
B.
romanizationFrom
Indicates that one entity is a romanized representation derived from the script or writing system of another entity.
-
C.
romanizationProcess
Indicates the process of converting text from a non-Latin writing system into a representation using the Latin alphabet.
-
D.
romanizationContext
Indicates the specific system, rules, or circumstances under which a script or language is converted into its romanized form.
-
E.
transliterationType
Indicates the specific system or method used to convert text from one writing system into another using corresponding characters.
- F. None of above. chosen
Provenance (4 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d886d090cc8190a39cb94992586905 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3dc2a7f2c81908eb19594b6accab7 |
completed | April 18, 2026, 7:31 p.m. |
| PD | Predicate disambiguation | batch_69e35d6b1b988190a8d6b6fe78c35e59 |
completed | April 18, 2026, 10:31 a.m. |
| PDg | Predicate description generation | batch_69e37542d060819082aa73948eb8ebd4 |
completed | April 18, 2026, 12:12 p.m. |
Created at: April 10, 2026, 5:35 a.m.